Implementation of a Multitudinous Face Recognition using YOLO.V3

Abstract

Face recognition is one of the most functional research in present scenario, with many practical and commercial applications including identification, access control, forensics, medical care, human-computer interactions, security, etc. Face recognition technique is rapidly becoming the mainstay of state of the art technological security solution. One of the crucial applications of face recognition in the current scenario is linked with security. Identifying people from a crowd or a group of people require an exceptional algorithm. One of the most arduous tasks about the existing face recognition system is the processing or prediction time. The current systems focus on accuracy than speed, which leads to an increase in the detection time. There are several techniques in machine learning and deep learning. But deep learning is preferred more than machine learning for detection and recognition applications because of the large availability of data. An algorithm for fast real-time object detecting and recognizing application is required. YOLO (you only look once) is a single shot deep learning object detection algorithm. In this work, the working of the YOLO algorithm and implementing multiple face recognition using YOLO version 3 is explained. A custom dataset is created from taken from Kaggle and google. At the time of testing the model, a processing speed of 30 ms was obtained.